To solve the trajectory tracking problem of underactuated surface vessels (USVs) under the condition of model uncertainty, strong coupling characteristics and controller input saturation, this study proposes a predefined time tracking control method for USVs based on input saturation.

Due to the non-zero diagonal terms and strong coupling characteristics of the USV model, coordinate transformation is introduced to transform the system model into a diagonal form. The predefined time performance function is combined with the barrier Lyapunov function (BLF) to ensure transient and stable tracking performance. Self-structuring neural networks (SSNN) are used to approximate unknown external disturbances and complex continuous unknown nonlinear terms, and deal with the impact of actuator saturation, thus ensuring the tracking performance of the control system. Moreover, the number of SSNN neurons can be adjusted online, reducing the computational burden on the control system.

Based on Lyapunov stability theory, it is proven that the closed-loop system is bounded stable in a predefined time, and the tracking error is always within the constraint range.

The simulation results show that the proposed control strategy is effective and has good tracking performance.